SafeAI 2019

The AAAI's Workshop on Artificial Intelligence Safety

The SafeAI Program is now available!

WHAT is about

SafeAI aims to explore new ideas on AI safety engineering, ethically aligned design, regulation and standards for AI-based systems.

SUBMIT a Contribution

You are invited to submit short position papers (2-4 pages), full technical papers (6-8 pages) or proposals for technical talks (one-page abstract).

Important DATES

Paper Submission: Nov 5
Acceptance Notification: Nov 26
Camera Ready Version: Dec 5

Workshop PROCEEDINGS

The workshop proceedings are now available on CEUR-WS.org.

Meet our SPEAKERS

SafeAI will be a memorable event with two top keynote speakers and three great invited talks.

Keynote and Invited Speakers

Proud to bring great inspirational speakers:

The DARPA Assured Autonomy program aims to advance the ways computing systems can learn and evolve with machine learning to better manage variations in the environment and enhance the predictability of autonomous systems like driverless vehicles.

Prof. Francesca Rossi, IBM and University of Padova

Keynote: Ethically Bounded AI

Humans and machines will often need to work together and agree on common decisions. We claim that it is possible to adapt current logic-based modelling and reasoning frameworks, such as soft constraints, CP-nets, and constraint-based scheduling under uncertainty, to model safety constraints, moral values, and ethical principles.

Dr. Peter Eckersley, Partnership on AI & EFF

Invited Talk: Impossibility and Uncertainty Theorems in AI Value Alignment

We show that impossibility theorems in ethics have implications for the design of powerful algorithmic systems, such as high-stakes AI applications or sufficiently rigid and rule-based bureaucracies.

Dr. Ian Goodfellow, Google Brain

Invited Talk: Adversarial Robustness for AI Safety

This talk addresses how it is important to develop robust models in order to make reward maximization safe, in order to make models succeed at learning to evaluate safety, and to evaluate human preferences.

Prof. Alessio R. Lomuscio, Imperial College London

Invited Talk: Reachability Analysis for Neural Agent-Environment Systems

We present a novel model for studying agent-environment systems, where the agents are implemented via feed-forward ReLU neural networks. We study several reachability problems for the system, ranging from one-step reachability, to fixed multi-step and arbitrary-step to study the system evolution.

SafeAI is a "sister" workshop to WAISE (hosted by SAFECOMP)

Get Involved

Venue

Hilton Hawaiian Village, Honolulu, Hawaii, USA. Hotel and Travel information.

For complete information about options in Honolulu, please see the Hawaiian Islands visitors page.

Registration

Late registration deadline: January 2, 2019. Full details about workshop registration are available at: AAAI-19 Registration.